HW3

機械一 謝承軒 B06502078

分析粉絲團厭世哲學家

一個有關道家思想的粉絲團

使用套件

library(Rfacebook)

## Loading required package: httr

## Loading required package: rjson

## Loading required package: httpuv

## 
## Attaching package: 'Rfacebook'

## The following object is masked from 'package:methods':
## 
##     getGroup

library(NLP)

## 
## Attaching package: 'NLP'

## The following object is masked from 'package:httr':
## 
##     content

library(tm)
library(jiebaRD)
library(jiebaR)
library(RColorBrewer)
library(wordcloud)
library(wordcloud2)

抓取資料

token  = "EAACEdEose0cBAD19wJh2AUR2I5oB97JDplFJ6zNCmlaBRToAo70qmQxiTWqJ1tk2NrCHLxO2bsnZBiWFYWMOZAbbGI0S1Gdg2vnDXIwV32KkJ8eIUImHEprkJqpjYAnlPZC9NZCMfjI3vbJpoJc9GYJ34wIli5mdCPB2MKqvLJPZCMMx38F0g9GN9yDzuhn5ZBJQhEcCfbSgZDZD"
page.id <- "866912333439333" 
page <- getPage(page.id, token, n = 50)

## 25 posts 50 posts

文本清理 並防止莊子老子被清掉

docs <- Corpus(VectorSource(as.character(page[,3])))
toSpace <- content_transformer(function(x,pattern){
  return (gsub(pattern," ",x))
})
docs <- tm_map(docs, toSpace, "※")
docs <- tm_map(docs, toSpace, "◆")
docs <- tm_map(docs, toSpace, "‧")
docs <- tm_map(docs, toSpace, "的")
docs <- tm_map(docs, toSpace, "我")
docs <- tm_map(docs, toSpace, "也")
docs <- tm_map(docs, toSpace, "他")
docs <- tm_map(docs, toSpace, "是")
docs <- tm_map(docs, toSpace, "就")
docs <- tm_map(docs, toSpace, "了")
docs <- tm_map(docs, toSpace, "在")
docs <- tm_map(docs, toSpace, "但")
docs <- tm_map(docs, toSpace, "都")
docs <- tm_map(docs, toSpace, "不")
docs <- tm_map(docs, toSpace, "與")
docs <- tm_map(docs, toSpace, "什麼")
docs <- tm_map(docs, toSpace, "一個")
docs <- tm_map(docs, toSpace, "們")
docs <- tm_map(docs, toSpace, "[a-zA-Z]")
docs <- tm_map(docs, removePunctuation)
docs <- tm_map(docs, removeNumbers)
docs <- tm_map(docs, stripWhitespace)
mixseg = worker()
new_user_word(mixseg,'老子','莊子')

## [1] TRUE

製作文字雲

jieba_tokenizer=function(d){
  unlist(segment(d[[1]],mixseg))
}
seg = lapply(docs, jieba_tokenizer)
freqFrame = as.data.frame(table(unlist(seg)))

wordcloud(freqFrame$Var1,freqFrame$Freq,
          min.freq=15,scale=c(4,.8),
          random.order=TRUE,random.color=FALSE, 
          rot.per=.1, colors=rainbow(length(row.names(freqFrame))),
          ordered.colors=TRUE,use.r.layout=FALSE,
          fixed.asp=TRUE)

分析結果

總結來說 這是一個蠻失敗的文字雲 能看出的資訊十分有限 1.因為道家思想的傳達多是包括自我的探討 所以你和自己這兩個字元出現十分多次 2.可能還要去一些贅字